Atrous Convolution

Atrous Convolution is a convolutional operation in deep learning that belongs to the family of convolution variants and is distinguished by its use of a dilation rate to control the spacing between kernel elements, enabling increased receptive field coverage without sacrificing spatial resolution or requiring additional parameters.

251

Publications

52.9K

Citations

1.1K

Authors

388

Institutions

Publications per year

2017–2026

250

Authors

1.1K

  1. LC
    Liang-Chieh Chen

    Google (United States), United States

    9 publications · 36.6K citations

    9

    h-index

  2. GP
    George Papandreou

    Google (United States), United States

    6 publications · 35.3K citations

    6

    h-index

  3. AY
    Alan Yuille

    Johns Hopkins University, United States

    5 publications · 24.1K citations

    5

    h-index

  4. FS
    Florian Schroff

    Google (United States), United States

    4 publications · 12.5K citations

    4

    h-index

  5. HA
    Hartwig Adam

    Google (United States), United States

    4 publications · 12.5K citations

    4

    h-index

1–5 of 1.1K

Venues

  1. Remote Sensing

    21 publications · 1.4K citations

    17

    h-index

  2. IEEE Access

    18 publications · 762 citations

    16

    h-index

  3. arXiv (Cornell University)

    Repository · 16 publications · 13.3K citations

    13

    h-index

  4. Applied Sciences

    7 publications · 361 citations

    7

    h-index

  5. 6

    h-index

1–5